Model comparison
GPT-4 vs Palm 2
GPT-4 and Palm 2 score almost the same on the Noometry Index (29.1 vs 30.0), so choose on price, context window or the category you care about most.
Last verified . 10 shared benchmarks.
GoogleSummary
- They share 10 benchmarks with published results for both. GPT-4 scores higher in 5 categories and Palm 2 in 2 categories; 7 gaps are clear of the uncertainty.
- The widest gap is in math, where Palm 2 leads 30.8 to 10.8.
Side by side
| GPT-4 | Palm 2 | |
|---|---|---|
| Provider | OpenAI | |
| Noometry Index | 29.1 | 30.0 |
| Released | 2023-03-14 | — |
| Weights | Proprietary | Proprietary |
| Context window | 8K | — |
| Max output | 8K | — |
| Input $ / M tokens | $30 | — |
| Output $ / M tokens | $60 | — |
| Results tracked | 38 | 10 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding GPT-4 leads
GPT-4: 31.6 (#283), Palm 2: 29.0 (#311)
| Benchmark | GPT-4 | Palm 2 |
|---|---|---|
| LMArena Coding | 1254 | 994 |
| WeirdML | 12.4% | — |
| BigCodeBench Instruct | 46% | — |
| BigCodeBench Complete | 57.2% | — |
| HumanEval+ | 79.3% | — |
Agentic & Tool Use Not comparable
GPT-4: —, Palm 2: —
| Benchmark | GPT-4 | Palm 2 |
|---|---|---|
| METR Time Horizons | 36.1% | — |
Reasoning Palm 2 leads
GPT-4: 17.8 (#289), Palm 2: 19.1 (#271)
| Benchmark | GPT-4 | Palm 2 |
|---|---|---|
| LMArena Hard Prompts | 1241 | 1005 |
| Chess Puzzles | 4% | — |
| Mystery Game Puzzles | 12% | — |
| DTBench | 62.7% | — |
| LMCA | 17.1% | — |
| BIG-Bench Hard | 75.1% | — |
| Epoch Capabilities Index | 125.89 | — |
| ForecastBench | 57.8 | — |
| HellaSwag | 95.3% | — |
| WinoGrande | 87.5% | — |
Math Palm 2 leads
GPT-4: 10.8 (#309), Palm 2: 30.8 (#231)
| Benchmark | GPT-4 | Palm 2 |
|---|---|---|
| LMArena Math | 1269 | 1049 |
| OTIS Mock AIME 2024-2025 | 1.1% | — |
| MATH Level 5 | 23% | — |
| GSM8K | 92% | — |
Knowledge Not comparable
GPT-4: 18.4 (#282), Palm 2: —
| Benchmark | GPT-4 | Palm 2 |
|---|---|---|
| GPQA Diamond | 35.7% | — |
| LMArena Expert | 1211 | — |
| MMLU | 86.4% | — |
| TriviaQA | 84.8% | — |
Multilingual GPT-4 leads
GPT-4: 40.6 (#215), Palm 2: 20.9 (#295)
| Benchmark | GPT-4 | Palm 2 |
|---|---|---|
| LMArena Non-English | 1246 | 916 |
| LMArena Chinese | 1242 | 887 |
| LMArena French | 1283 | — |
| LMArena German | 1251 | — |
| LMArena Japanese | 1209 | — |
| LMArena Korean | 1184 | — |
| LMArena Russian | 1251 | — |
| LMArena Spanish | 1261 | — |
Instruction Following GPT-4 leads
GPT-4: 65.3 (#222), Palm 2: 51.0 (#296)
| Benchmark | GPT-4 | Palm 2 |
|---|---|---|
| LMArena Instruction Following | 1241 | 1010 |
Long Context GPT-4 leads
GPT-4: 37.7 (#212), Palm 2: 30.8 (#285)
| Benchmark | GPT-4 | Palm 2 |
|---|---|---|
| LMArena Longer Query | 1244 | 1010 |
Writing & Preference GPT-4 leads
GPT-4: 34.9 (#268), Palm 2: 25.6 (#304)
| Benchmark | GPT-4 | Palm 2 |
|---|---|---|
| LMArena Text | 1263 | 1027 |
| LMArena Creative Writing | 1244 | 991 |
| LMArena Multi-Turn | 1257 | 994 |
| EQ-Bench Creative Writing | 752 | — |
Frequently asked questions
Is GPT-4 better than Palm 2?
GPT-4 and Palm 2 score almost the same on the Noometry Index (29.1 vs 30.0), so choose on price, context window or the category you care about most.
Is GPT-4 or Palm 2 better for coding?
GPT-4 scores higher on coding benchmarks: 31.6 versus 29.0 in the Noometry coding category.
How many benchmarks do GPT-4 and Palm 2 share?
10 benchmarks have published results for both models. GPT-4 has 38 scored results on Noometry and Palm 2 has 10.